Embedding entities and relations into continuous vector spaces has attracted a surge of interest in recent years. Most embedding methods assume that all test entities are available during training, which makes it time-consuming to retrain embeddings for newly emerging entities. To address this issue, recent works apply the graph neural network on the existing neighbors of the unseen entities. In this paper, we propose a novel framework, namely Virtual Neighbor (VN) network, to address three key challenges. Firstly, to reduce the neighbor sparsity problem, we introduce the concept of the virtual neighbors inferred by rules. And we assign soft labels to these neighbors by solving a rule-constrained problem, rather than simply regarding them as unquestionably true. Secondly, many existing methods only use one-hop or two-hop neighbors for aggregation and ignore the distant information that may be helpful. Instead, we identify both logic and symmetric path rules to capture complex patterns. Finally, instead of one-time injection of rules, we employ an iterative learning scheme between the embedding method and virtual neighbor prediction to capture the interactions within. Experimental results on two knowledge graph completion tasks demonstrate that our VN network significantly outperforms state-of-the-art baselines. Furthermore, results on Subject/Object-R show that our proposed VN network is highly robust to the neighbor sparsity problem.

Are Large Language Models as Stochastic Parroting without any Intellect? Language models may be categorized as probabilistic methods and neural network-based modern language models. A simple probabilistic language model that calculates n-gram probabilities has significant drawbacks. The major one is the context problem. Complicated texts have deep context influencing the choice of the next word.

Recurrent Neural Networks (RNNs) have achieved tremendous success in sequential data processing. However, it is quite challenging to interpret and verify RNNs' behaviors directly. To this end, many efforts have been made to extract finite automata from RNNs. Existing approaches such as exact learning are effective in extracting finite-state models to characterize the state dynamics of RNNs for formal languages, but are limited in the scalability to process natural languages. Compositional approaches that are scablable to natural languages fall short in extraction precision. In this paper, we identify the transition sparsity problem that heavily impacts the extraction precision. To address this problem, we propose a transition rule extraction approach, which is scalable to natural language processing models and effective in improving extraction precision. Specifically, we propose an empirical method to complement the missing rules in the transition diagram. In addition, we further adjust the transition matrices to enhance the context-aware ability of the extracted weighted finite automaton (WFA). Finally, we propose two data augmentation tactics to track more dynamic behaviors of the target RNN. Experiments on two popular natural language datasets show that our method can extract WFA from RNN for natural language processing with better precision than existing approaches. Our code is available at https://github.com/weizeming/Extract_WFA_from_RNN_for_NL.

The overwhelming amount of short text data on social media and elsewhere has posed great challenges to topic modeling due to the sparsity problem. Most existing attempts to alleviate this problem resort to heuristic strategies to aggregate short texts into pseudo-documents before the application of standard topic modeling. Although such strategies cannot be well generalized to more general genres of short texts, the success has shed light on how to develop a generalized solution. In this paper, we present a novel model towards this goal by integrating topic modeling with short text aggregation during topic inference. The aggregation is founded on general topical affinity of texts rather than particular heuristics, making the model readily applicable to various short texts. Experimental results on real-world datasets validate the effectiveness of this new model, suggesting that it can distill more meaningful topics from short texts.

Cross-domain recommendation has been proposed to transfer user behavior pattern by pooling together the rating data from multiple domains to alleviate the sparsity problem appearing in single rating domains. However, previous models only assume that multiple domains share a latent common rating pattern based on the user-item co-clustering. To capture diversities among different domains, we propose a novel Probabilistic Cluster-level Latent Factor (PCLF) model to improve the cross-domain recommendation performance. Experiments on several real world datasets demonstrate that our proposed model outperforms the state-of-the-art methods for the cross-domain recommendation task.

Recent results in Compressive Sensing have shown that, under certain conditions, the solution to an underdetermined system of linear equations with sparsity-based regularization can be accurately recovered by solving convex relaxations of the original problem. In this work, we present a novel primal-dual analysis on a class of sparsity minimization problems. We show that the Lagrangian bidual (i.e., the Lagrangian dual of the Lagrangian dual) of the sparsity minimization problems can be used to derive interesting convex relaxations: the bidual of the $\ell_0$-minimization problem is the $\ell_1$-minimization problem; and the bidual of the $\ell_{0,1}$-minimization problem for enforcing group sparsity on structured data is the $\ell_{1,\infty}$-minimization problem. The analysis provides a means to compute per-instance non-trivial lower bounds on the (group) sparsity of the desired solutions. In a real-world application, the bidual relaxation improves the performance of a sparsity-based classification framework applied to robust face recognition.

Subjective assessments (SAs) are assigned by users against items, such as ’elegant’ and ’gorgeous’, and are common in reviews/tags in many online-sites. However, previous studies fail to effectively use SAs for improving recommendations because few users rate the same items with the same SAs, which triggers the sparsity problem in collaborative filtering. We propose a novel algorithm that links a taxonomy of items to a taxonomy of SAs to assess user interests in detail. That is, it merges the SAs assigned by users against an item into subjective classes (SCs) and reflects the SAs/SCs assigned to an item to its classes. Thus, it can measure the similarity of users from not only SAs/SCs assigned to items but also their classes, which overcomes the sparsity problem. Our evaluation, which uses data from a popular restaurant review site, shows that our method generates more accurate recommendations than previous methods. Furthermore, we find that SAs frequently assigned on a few item classes are more useful than those widely assigned against many item classes in terms of recommendation accuracy.

The sparsity problem in collaborative filtering (CF) is a major bottleneck for most CF methods. In this paper, we consider a novel approach for alleviating the sparsity problem in CF by transferring user-item rating patterns from a dense auxiliary rating matrix in other domains (e.g., a popular movie rating website) to a sparse rating matrix in a target domain (e.g., a new book rating website). We do not require that the users and items in the two domains be identical or even overlap. Based on the limited ratings in the target matrix, we establish a bridge between the two rating matrices at a cluster-level of user-item rating patterns in order to transfer more useful knowledge from the auxiliary task domain. We first compress the ratings in the auxiliary rating matrix into an informative and yet compact cluster-level rating pattern representation referred to as a codebook. Then, we propose an efficient algorithm for reconstructing the target rating matrix by expanding the codebook. We perform extensive empirical tests to show that our method is effective in addressing the data sparsity problem by transferring the useful knowledge from the auxiliary tasks, as compared to many state-of-the-art CF methods.